© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20745
    Prev
    Next
    INDEX
    Explanations

    word list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èİ«
    -0.12
    æ´Ħ
    -0.11
    奴
    -0.10
    个å°ı
    -0.09
    ยาว
    -0.09
    ENDED
    -0.09
    æĺİ亮
    -0.09
    èĭĶ
    -0.09
    ç©Ĩ
    -0.09
     subparagraph
    -0.09
    POSITIVE LOGITS
    éĺĬ
    0.08
    嵩
    0.08
    ç¦ģå¿Į
    0.08
    è¿Ļè¾¹
    0.08
     Chap
    0.08
    ä¸Ńæĸ°
    0.07
    ught
    0.07
    SI
    0.07
     memo
    0.07
     fountain
    0.07
    Activations Density 0.020%

    No Known Activations